Pull Kselftest updates from Shuah Khan: "Fixes to compile time errors and warnings" * tag 'linux-kselftest-next-5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest: selftests/core: fix conflicting types compile error for close_range() selftests: x86: fix [-Wstringop-overread] warn in test_process_vm_readv() selftests: kvm: fix mismatched fclose() after popen()
Pull x86 core updates from Borislav Petkov: - Do not #GP on userspace use of CLI/STI but pretend it was a NOP to keep old userspace from breaking. Adjust the corresponding iopl selftest to that. - Improve stack overflow warnings to say which stack got overflowed and raise the exception stack sizes to 2 pages since overflowing the single page of exception stack is very easy to do nowadays with all the tracing machinery enabled. With that, rip out the custom mapping of AMD SEV's too. - A bunch of changes in preparation for FGKASLR like supporting more than 64K section headers in the relocs tool, correct ORC lookup table size to cover the whole kernel .text and other adjustments. * tag 'x86_core_for_v5.16_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: selftests/x86/iopl: Adjust to the faked iopl CLI/STI usage vmlinux.lds.h: Have ORC lookup cover entire _etext - _stext x86/boot/compressed: Avoid duplicate malloc() implementations x86/boot: Allow a "silent" kaslr random byte fetch x86/tools/relocs: Support >64K section headers x86/sev: Make the #VC exception stacks part of the default stacks storage x86: Increase exception stack sizes x86/mm/64: Improve stack overflow warnings x86/iopl: Fake iopl(3) CLI/STI usage
Commit in Fixes changed the iopl emulation to not #GP on CLI and STI
because it would break some insane luserspace tools which would toggle
interrupts.
The corresponding selftest would rely on the fact that executing CLI/STI
would trigger a #GP and thus detect it this way but since that #GP is
not happening anymore, the detection is now wrong too.
Extend the test to actually look at the IF flag and whether executing
those insns had any effect on it. The STI detection needs to have the
fact that interrupts were previously disabled, passed in so do that from
the previous CLI test, i.e., STI test needs to follow a previous CLI one
for it to make sense.
Fixes: b968e84b509d ("x86/iopl: Fake iopl(3) CLI/STI usage")
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20211030083939.13073-1-bp@alien8.de
XSAVE state is thread-local. The kernel switches between thread state at context switch time. Generally, running a selftest for a while will naturally expose it to some context switching and and will test the XSAVE code. Instead of just hoping that the tests get context-switched at random times, force context-switches on purpose. Spawn off a few userspace threads and force context-switches between them. Ensure that the kernel correctly context switches each thread's unique AMX state. [ dhansen: bunches of cleanups ] Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Link: https://lkml.kernel.org/r/20211026122525.6EFD5758@davehans-spike.ostc.intel.com
AMX TILEDATA is a very large XSAVE feature. It could have caused nasty XSAVE buffer space waste in two places: * Signal stacks * Kernel task_struct->fpu buffers To avoid this waste, neither of these buffers have AMX state by default. The non-default features are called "dynamic" features. There is an arch_prctl(ARCH_REQ_XCOMP_PERM) which allows a task to declare that it wants to use AMX or other "dynamic" XSAVE features. This arch_prctl() ensures that sufficient sigaltstack space is available before it will succeed. It also expands the task_struct buffer. Functions of this test: * Test arch_prctl(ARCH_REQ_XCOMP_PERM). Ensure that it checks for proper sigaltstack sizing and that the sizing is enforced for future sigaltstack calls. * Ensure that ARCH_REQ_XCOMP_PERM is inherited across fork() * Ensure that TILEDATA use before the prctl() is fatal * Ensure that TILEDATA is cleared across fork() Note: Generally, compiler support is needed to do something with AMX. Instead, directly load AMX state from userspace with a plain XSAVE. Do not depend on the compiler. [ dhansen: bunches of cleanups ] Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Link: https://lkml.kernel.org/r/20211026122524.7BEDAA95@davehans-spike.ostc.intel.com
Fix the following [-Wstringop-overread] by passing in the variable
instead of the value.
test_vsyscall.c: In function ‘test_process_vm_readv’:
test_vsyscall.c:500:22: warning: ‘__builtin_memcmp_eq’ specified bound 4096 exceeds source size 0 [-Wstringop-overread]
500 | if (!memcmp(buf, (const void *)0xffffffffff600000, 4096)) {
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
A glibc 2.34 feature adds support for variable MINSIGSTKSZ and SIGSTKSZ. When _DYNAMIC_STACK_SIZE_SOURCE or _GNU_SOURCE are defined, MINSIGSTKSZ and SIGSTKSZ are no longer constant on Linux. glibc 2.34 flags code paths assuming MINSIGSTKSZ or SIGSTKSZ are constant. Fix these error in x86 test. Feature description and build error: NEWS for version 2.34 ===================== Major new features: * Add _SC_MINSIGSTKSZ and _SC_SIGSTKSZ. When _DYNAMIC_STACK_SIZE_SOURCE or _GNU_SOURCE are defined, MINSIGSTKSZ and SIGSTKSZ are no longer constant on Linux. MINSIGSTKSZ is redefined to sysconf(_SC_MINSIGSTKSZ) and SIGSTKSZ is redefined to sysconf (_SC_SIGSTKSZ). This supports dynamic sized register sets for modern architectural features like Arm SVE. ===================== If _SC_SIGSTKSZ_SOURCE or _GNU_SOURCE are defined, MINSIGSTKSZ and SIGSTKSZ are redefined as: /* Default stack size for a signal handler: sysconf (SC_SIGSTKSZ). */ # undef SIGSTKSZ # define SIGSTKSZ sysconf (_SC_SIGSTKSZ) /* Minimum stack size for a signal handler: SIGSTKSZ. */ # undef MINSIGSTKSZ # define MINSIGSTKSZ SIGSTKSZ Compilation will fail if the source assumes constant MINSIGSTKSZ or SIGSTKSZ. Build error with the GNU C Library 2.34: DEBUG: | sigreturn.c:150:13: error: variably modified 'altstack_data' at file scope | sigreturn.c:150:13: error: variably modified 'altstack_data' at file scope DEBUG: | 150 | static char altstack_data[SIGSTKSZ]; | 150 | static char altstack_data[SIGSTKSZ]; DEBUG: | | ^~~~~~~~~~~~~ DEBUG: | single_step_syscall.c:60:22: error: variably modified 'altstack_data' at file scope DEBUG: | 60 | static unsigned char altstack_data[SIGSTKSZ]; DEBUG: | | ^~~~~~~~~~~~~ Fixed commit log to improve formatting and clarity: Shuah Khan <skhan@linuxfoundation.org> Link: https://sourceware.org/pipermail/libc-alpha/2021-January/121996.html Link: https://sourceware.org/pipermail/libc-alpha/2021-August/129718.html Suggested-by: Jianwei Hu <jianwei.hu@windriver.com> Signed-off-by: Jun Miao <jun.miao@windriver.com> Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Pull x86 fpu updates from Thomas Gleixner:
"Fixes and improvements for FPU handling on x86:
- Prevent sigaltstack out of bounds writes.
The kernel unconditionally writes the FPU state to the alternate
stack without checking whether the stack is large enough to
accomodate it.
Check the alternate stack size before doing so and in case it's too
small force a SIGSEGV instead of silently corrupting user space
data.
- MINSIGSTKZ and SIGSTKSZ are constants in signal.h and have never
been updated despite the fact that the FPU state which is stored on
the signal stack has grown over time which causes trouble in the
field when AVX512 is available on a CPU. The kernel does not expose
the minimum requirements for the alternate stack size depending on
the available and enabled CPU features.
ARM already added an aux vector AT_MINSIGSTKSZ for the same reason.
Add it to x86 as well.
- A major cleanup of the x86 FPU code. The recent discoveries of
XSTATE related issues unearthed quite some inconsistencies,
duplicated code and other issues.
The fine granular overhaul addresses this, makes the code more
robust and maintainable, which allows to integrate upcoming XSTATE
related features in sane ways"
* tag 'x86-fpu-2021-07-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (74 commits)
x86/fpu/xstate: Clear xstate header in copy_xstate_to_uabi_buf() again
x86/fpu/signal: Let xrstor handle the features to init
x86/fpu/signal: Handle #PF in the direct restore path
x86/fpu: Return proper error codes from user access functions
x86/fpu/signal: Split out the direct restore code
x86/fpu/signal: Sanitize copy_user_to_fpregs_zeroing()
x86/fpu/signal: Sanitize the xstate check on sigframe
x86/fpu/signal: Remove the legacy alignment check
x86/fpu/signal: Move initial checks into fpu__restore_sig()
x86/fpu: Mark init_fpstate __ro_after_init
x86/pkru: Remove xstate fiddling from write_pkru()
x86/fpu: Don't store PKRU in xstate in fpu_reset_fpstate()
x86/fpu: Remove PKRU handling from switch_fpu_finish()
x86/fpu: Mask PKRU from kernel XRSTOR[S] operations
x86/fpu: Hook up PKRU into ptrace()
x86/fpu: Add PKRU storage outside of task XSAVE buffer
x86/fpu: Dont restore PKRU in fpregs_restore_userspace()
x86/fpu: Rename xfeatures_mask_user() to xfeatures_mask_uabi()
x86/fpu: Move FXSAVE_LEAK quirk info __copy_kernel_to_fpregs()
x86/fpu: Rename __fpregs_load_activate() to fpregs_restore_userregs()
...
This is very heavily based on some code from Thomas Gleixner. On a system without XSAVES, it triggers the WARN_ON(): Bad FPU state detected at copy_kernel_to_fpregs+0x2f/0x40, reinitializing FPU registers. [ bp: Massage in nitpicks. ] Signed-off-by: Andy Lutomirski <luto@kernel.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Dave Hansen <dave.hansen@linux.intel.com> Acked-by: Rik van Riel <riel@surriel.com> Link: https://lkml.kernel.org/r/20210608144346.234764986@linutronix.de
Add tests running under ptrace for syscall_numbering_64. ptrace stopping on syscall entry and possibly modifying the syscall number (regs.orig_rax) or the default return value (regs.rax) can have different results than the normal system call path. Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Link: https://lore.kernel.org/r/20210518191303.4135296-4-hpa@zytor.com